Impact of Image Pre-processing Methods on Computed Tomography Radiomics Features in Chronic Obstructive Pulmonary Disease

Computed tomography (CT) imaging texture-based radiomics analysis can be used to assess chronic obstructive pulmonary disease (COPD). However, different image pre-processing methods that are commonly used, and how these different methods impact radiomics features and lung disease assessment, is unknown. Here, an image pre-processing pipeline was developed to investigate how various pre-processing combinations impact radiomics features and their use for COPD assessment. Image pre-processing techniques that were investigated included airway segmentation, image resampling, and application of either no pre-processing, binning, edgmentation, or thresholding pre-processing techniques. Image resampling and the different preprocessing techniques had the greatest effect on radiomics features. Features generated using the resampling/edgmentation and resampling/thresholding combinations, regardless of airway segmentation, performed the best in COPD classification, and explained the most variance with 2 lung function (R ≥0.353). Therefore, the image pre-processing methods completed prior to CT radiomics feature extraction significantly impacted extracted features and their ability to assess COPD.